<br>

🎨 dsh-media-skills

Give DeepSeek Harness eyes — and a brush. Read images in any chat, generate new ones, all with free models.

<br>

DeepSeek Harness is brilliant at reasoning — but a text-only model can't see the image you just dragged into the chat. This bundle fixes that with two free skills, a free vision model route, and a vision engine failover chain:

• 📎 Paste to read — paste, drag, or pick an image in any session; the free vision model turns it into text your current model understands. (Native on v0.1.6 / v0.1.1; on rc.7 / rc.8 via the bundled core patches — see docs/HARNESS_PATCH_EN.md.)
• 👁️ vision-review — analyze images and screenshots, catch UI visual bugs, detect watermarks, turn images into text.
• 🎨 media-tools — generate illustrations, avatars, backgrounds and banners with a free, watermark-free model.
• 🔀 Engine failover — GLM-4V-Flash (free) → DeepSeek-V4-Flash-Vision-Exp (same key as your agent, higher quality) → SiliconFlow Qwen3-VL → SenseNova → Google Gemini (AI Studio) → any OpenAI-compatible endpoint, with ModLens-style structured evidence output.

No hardcoded keys, no paid API, no file saving, no session switching.

Why · Quick start · See it in action · Usage · Keys & privacy · FAQ · Examples

English · 简体中文 · 繁體中文 · 日本語 · 한국어 · Español · Deutsch · Português · Русский

---

🤔 Why

Most DSH vision plugins only read images — and many push you through a shared third-party endpoint. dsh-media-skills takes a different stance:

	This bundle	Typical vision-only plugin
Read images for free	✅ GLM-4V-Flash (free) · DeepSeek-V4-Flash-Vision-Exp (v0.1.1 default, same key)	✅
Generate images for free	✅ SenseNova U1 Fast → SiliconFlow Kolors	❌ usually absent
Auto model route in the picker	✅ automatic on ≤ v0.1.1 · on v0.1.6 you pick it in Settings → Models (the plugin never writes settings)	sometimes
Keys committed to the repo	❌ never — keys stay local	⚠️ often required
Docs in multiple languages	✅ 9 languages	❌ usually English only
Privacy	✅ you choose the provider; images only go to your provider	shared free endpoints can see your images

Why bring your own free key instead of a built-in anonymous endpoint? Privacy and reliability. Your images go only to the provider you choose, under your account and your rate limits — no shared third-party service in the middle.

New-version adaptation: on DeepSeek Harness v0.1.6, image attachments are native and this bundle installs as a standard runtime plugin — no core patches, no settings writes; you add or pick model routes yourself in Settings → Models. On v0.1.1-rc.1 / rc.2, the deepseek-official route ships DeepSeek-V4-Flash-Vision-Exp natively — paste-image transcription and the vision model route pick it up automatically with the key your agent already uses (zero extra keys). rc.7 / rc.8 apply the bundled patches (see HARNESS_PATCH, historical).

✨ What you get

…